© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44233
    Prev
    Next
    INDEX
    Explanations

    figurative language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    婇
    0.43
    .",[
    0.41
    гром
    0.41
    ို့
    0.40
    ",[
    0.40
     버전
    0.40
    ố
    0.39
    ㎥
    0.39
    лизова
    0.39
    튬
    0.38
    POSITIVE LOGITS
     Brink
    0.49
     Br
    0.47
     d
    0.46
     Beautiful
    0.46
     Dion
    0.45
    店铺
    0.45
     whirlpool
    0.45
     Brew
    0.44
     ito
    0.43
    sailboat
    0.43
    Activations Density 0.006%

    No Known Activations